English
Related papers

Related papers: Multi-scale Octave Convolutions for Robust Speech …

200 papers

Convolutional Neural Networks (CNNs) are state-of-the-art in numerous computer vision tasks such as object classification and detection. However, the large amount of parameters they contain leads to a high computational complexity and…

Machine Learning · Computer Science 2019-01-01 Ghouthi Boukli Hacene , Vincent Gripon , Matthieu Arzel , Nicolas Farrugia , Yoshua Bengio

In this paper, we explore an improved framework to train a monoaural neural enhancement model for robust speech recognition. The designed training framework extends the existing mixture invariant training criterion to exploit both unpaired…

Sound · Computer Science 2022-09-21 Jisi Zhang , Catalin Zorila , Rama Doddipatla , Jon Barker

A convolutional layer in a Convolutional Neural Network (CNN) consists of many filters which apply convolution operation to the input, capture some special patterns and pass the result to the next layer. If the same patterns also occur at…

Computer Vision and Pattern Recognition · Computer Science 2019-02-04 Okan Köpüklü , Maryam Babaee , Stefan Hörmann , Gerhard Rigoll

This paper introduces AdaptoVision, a novel convolutional neural network (CNN) architecture designed to efficiently balance computational complexity and classification accuracy. By leveraging enhanced residual units, depth-wise separable…

Computer Vision and Pattern Recognition · Computer Science 2025-07-02 Md. Sanaullah Chowdhury Lameya Sabrin

Robust audio-visual speech recognition (AVSR) in noisy environments remains challenging, as existing systems struggle to estimate audio reliability and dynamically adjust modality reliance. We propose router-gated cross-modal feature…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 DongHoon Lim , YoungChae Kim , Dong-Hyun Kim , Da-Hee Yang , Joon-Hyuk Chang

It has been shown that the intelligibility of noisy speech can be improved by speech enhancement (SE) algorithms. However, monaural SE has not been established as an effective frontend for automatic speech recognition (ASR) in noisy…

Sound · Computer Science 2024-03-12 Yufeng Yang , Ashutosh Pandey , DeLiang Wang

This paper presents a novel convolutional layer, called perturbed convolution (PConv), which focuses on achieving two goals simultaneously: improving the generative adversarial network (GAN) performance and alleviating the memorization…

Computer Vision and Pattern Recognition · Computer Science 2021-12-23 Seung Park , Yoon-Jae Yeo , Yong-Goo Shin

In this paper, we propose hybrid real- and complex-valued neural networks for speech enhancement. Real- or complex-valued models are either inefficient or present high complexity. We devise a straightforward design method for extending a…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-26 Luan Vinícius Fiorio , Alex Young , Ronald M. Aarts

We introduce a new audio processing technique that increases the sampling rate of signals such as speech or music using deep convolutional neural networks. Our model is trained on pairs of low and high-quality audio examples; at test-time,…

Sound · Computer Science 2017-08-03 Volodymyr Kuleshov , S. Zayd Enam , Stefano Ermon

Attenuation coefficient (AC) is a fundamental measure of tissue acoustical properties, which can be used in medical diagnostics. In this work, we investigate the feasibility of using convolutional neural networks (CNNs) to directly estimate…

Medical Physics · Physics 2022-05-20 Piotr Jarosik , Michal Byra , Marcin Lewandowski , Ziemowit Klimonda

We present techniques for speeding up the test-time evaluation of large convolutional networks, designed for object recognition tasks. These models deliver impressive accuracy but each image evaluation requires millions of floating point…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Remi Denton , Wojciech Zaremba , Joan Bruna , Yann LeCun , Rob Fergus

Incremental improvements in accuracy of Convolutional Neural Networks are usually achieved through use of deeper and more complex models trained on larger datasets. However, enlarging dataset and models increases the computation and storage…

Audio and Speech Processing · Electrical Eng. & Systems 2018-07-24 Mahdi Hajibabaei , Dengxin Dai

Deep convolutional networks have attracted great attention in image restoration and enhancement. Generally, restoration quality has been improved by building more and more convolutional block. However, these methods mostly learn a specific…

Computer Vision and Pattern Recognition · Computer Science 2021-05-21 Yukai Shi , Jinghui Qin

Convolutional neural networks (CNNs), such as the time-delay neural network (TDNN), have shown their remarkable capability in learning speaker embedding. However, they meanwhile bring a huge computational cost in storage size, processing,…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-22 Rui Wang , Zhihua Wei , Haoran Duan , Shouling Ji , Yang Long , Zhen Hong

Convolutional Neural Networks (CNNs) have advanced significantly in visual representation learning and recognition. However, they face notable challenges in performance and computational efficiency when dealing with real-world, multi-scale…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Wenzhuo Liu , Fei Zhu , Cheng-Lin Liu

Spatial resolution in optical microscopy has traditionally been treated as a fixed parameter of the optical system. Here, we present an approach to enhance transverse resolution in beam-scanned optical coherence tomography (OCT) beyond its…

Optics · Physics 2021-10-22 Nichaluk Leartprapun , Steven G. Adie

This paper introduces MR-CQTdiff, a novel neural-network architecture for diffusion-based audio generation that leverages a multi-resolution Constant-$Q$ Transform (C$Q$T). The proposed architecture employs an efficient, invertible CQT…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-23 Maurício do V. M. da Costa , Eloi Moliner

The convolution neural nets (conv nets) have achieved a state-of-the-art performance in many applications of image and video processing. The most recent studies illustrate that the conv nets are fragile in terms of recognition accuracy to…

Computer Vision and Pattern Recognition · Computer Science 2019-10-25 Sergey Tarasenko , Fumihiko Takahashi

Model compression and acceleration are attracting increasing attentions due to the demand for embedded devices and mobile applications. Research on efficient convolutional neural networks (CNNs) aims at removing feature redundancy by…

Machine Learning · Computer Science 2020-08-21 Jinhua Liang , Tao Zhang , Guoqing Feng

Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-14 Wenyong Huang , Wenchao Hu , Yu Ting Yeung , Xiao Chen